nuke/cmd/anubis/botPolicies.json
Xe Iaso 9923878c5c
initial import from /x/ monorepo
Signed-off-by: Xe Iaso <me@xeiaso.net>
2025-03-17 19:33:07 -04:00

70 lines
1.6 KiB
JSON

{
"bots": [
{
"name": "amazonbot",
"user_agent_regex": "Amazonbot",
"action": "DENY"
},
{
"name": "googlebot",
"user_agent_regex": "\\+http\\:\\/\\/www\\.google\\.com/bot\\.html",
"action": "ALLOW"
},
{
"name": "bingbot",
"user_agent_regex": "\\+http\\:\\/\\/www\\.bing\\.com/bingbot\\.htm",
"action": "ALLOW"
},
{
"name": "qwantbot",
"user_agent_regex": "\\+https\\:\\/\\/help\\.qwant\\.com/bot/",
"action": "ALLOW"
},
{
"name": "us-artificial-intelligence-scraper",
"user_agent_regex": "\\+https\\:\\/\\/github\\.com\\/US-Artificial-Intelligence\\/scraper",
"action": "DENY"
},
{
"name": "well-known",
"path_regex": "^/.well-known/.*$",
"action": "ALLOW"
},
{
"name": "favicon",
"path_regex": "^/favicon.ico$",
"action": "ALLOW"
},
{
"name": "robots-txt",
"path_regex": "^/robots.txt$",
"action": "ALLOW"
},
{
"name": "rss-readers",
"path_regex": ".*\\.(rss|xml|atom|json)$",
"action": "ALLOW"
},
{
"name": "lightpanda",
"user_agent_regex": "^Lightpanda/.*$",
"action": "DENY"
},
{
"name": "headless-chrome",
"user_agent_regex": "HeadlessChrome",
"action": "DENY"
},
{
"name": "headless-chromium",
"user_agent_regex": "HeadlessChromium",
"action": "DENY"
},
{
"name": "generic-browser",
"user_agent_regex": "Mozilla",
"action": "CHALLENGE"
}
],
"dnsbl": true
}